Publications
Detailed Information
Enhanced Exemplar Based Inpainting Using Patch Ratio : 패치 간 비율을 이용해 개선된 표본을 바탕으로한 사라진 이미지 채우기
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 강명주 | - |
dc.contributor.author | 김상연 | - |
dc.date.accessioned | 2017-07-19T09:00:28Z | - |
dc.date.available | 2017-07-19T09:00:28Z | - |
dc.date.issued | 2015-02 | - |
dc.identifier.other | 000000025234 | - |
dc.identifier.uri | https://hdl.handle.net/10371/131494 | - |
dc.description | 학위논문 (석사)-- 서울대학교 대학원 : 수리과학부, 2015. 2. 강명주. | - |
dc.description.abstract | Image inpainting is the art of modyng part of image or video that cannot
detectable by ordinary observer. There are two dierent classes of algorithms for inpainting. Texture synthesis, and geometric partial dierential equations(PDEs). We think that we don't have to make new color in image so we only focus on nd the best matching pixels for each unknown pixels. In this paper, we suggest a new method based on exemplar based inpainting. The method is suggested by Criminisi et al. [1]. But its method takes a long time, but also cannot give a good result for some cases. First, we analyze deciency of Criminisi algorithm and then we oer a new algorithm. Our algorithm uses a modied calculation for priority and then uses patch ratio for nding the best candidates. For faster computing, we use window and number of nonzero elements of candidates. Finally, among the candidates we concern about gradients of the template. | - |
dc.description.tableofcontents | Abstract
1 Introduction 2 Inpainting Algorithm of Criminisi et al. 2.1 Motivaltion of the algorithm 2.1.1 Priority Calculation 2.1.2 Texture Synthesis 2.2 Criminisi Algorithm 3 Our Algorithm 3.1 Calculate priorities of exemplar blocks 3.2 Patch Ratio for Choosing Best Matching Block 3.3 Patch Energy term 4 Results 5 Conclusion Abstract (in Korean) Acknowledgement (in Korean) | - |
dc.format | application/pdf | - |
dc.format.extent | 4172896 bytes | - |
dc.format.medium | application/pdf | - |
dc.language.iso | en | - |
dc.publisher | 서울대학교 대학원 | - |
dc.subject | Image Inpainting | - |
dc.subject | Exemplar Based Inpainting | - |
dc.subject | Patch Ratio | - |
dc.subject | Texture Synthesis | - |
dc.subject | Template Matching | - |
dc.subject.ddc | 510 | - |
dc.title | Enhanced Exemplar Based Inpainting Using Patch Ratio | - |
dc.title.alternative | 패치 간 비율을 이용해 개선된 표본을 바탕으로한 사라진 이미지 채우기 | - |
dc.type | Thesis | - |
dc.contributor.AlternativeAuthor | KIM SANGYEON | - |
dc.description.degree | Master | - |
dc.citation.pages | iii, 21 | - |
dc.contributor.affiliation | 자연과학대학 수리과학부 | - |
dc.date.awarded | 2015-02 | - |
- Appears in Collections:
- Files in This Item:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.